Health Discovery Corporation Announces Filing of Patent Application Covering Methods for Enhancing Accuracy of Biomarker Discovery

SAVANNAH, GA -- 04/04/2005 -- Health Discovery Corporation (OTC BB: HDVY) today announced that it has filed an application in the United States Patent and Trademark Office for patent protection of its latest discoveries relating to machine learning-based classification of data from diagnostic assays. These discoveries address the oft-encountered problem of determining statistical significance within sample sets when the sample sets are relatively small. Sample set size is commonly limited by the time and costs of collecting and processing samples and measuring the resulting gene expression. Small sample set size can cast doubt on the reliability of the biomarker discovery process and the prediction of diagnostic accuracy. The normalization methods described in the patent application permit the combination of multiple data sets, including new data, old data, data generated by other laboratories, and even publicly available data, to provide increased accuracy in classification of data for reliable biomarker discovery. These methods also address many of the challenges that have resulted from the evolution of microarray technology, in which the configuration and number of probes per chip have changed over time, making it difficult to correlate data derived from different microarray configurations. The new methods were successfully used in the identification of sets of genetic biomarkers that provide a high degree of accuracy for distinguishing BPH (Benign Prostatic Hyperplasia) from prostate cancer and for distinguishing high-grade prostate cancers from less malignant grades. Biomarkers were also identified for separating BPH from normal prostate with a high degree of accuracy.

This new patent application adds additional value to Health Discovery Corporation’s patent portfolio which includes 10 issued U.S. and foreign patents covering among other things; applications of our support vector machine (SVM) technology and Recursive Feature Elimination (RFE) technology used in Support Vector Machines for biomarker discovery. The issued patents cover methods and systems for pre-processing data to enhance knowledge discovery using SVMs, analysis of data using multiple support vector machines and for multiple data sets, and providing SVM analysis services over the Internet while collecting financial compensation electronically in the process.

In addition, Health Discovery Corporation has over 65 pending patent applications for various techniques used in biomarker discovery as well as for newly discovered biomarkers. HDC’s pending U.S. and foreign patent applications cover numerous improvements to and applications of FGM techniques and SVM techniques, including computer-aided image analysis using SVMs, with particular application to diagnosis using medical images of digital mammography for breast cancer and images of blood for the identification of circulating tumor cells, methods of feature selection for enhanced SVM efficiency and new biomarkers discovered for colon cancer, prostate cancer, leukemia and renal cancer using these methods, as well as the use of SVMs for analysis of spectral data such as data generated in mass spectrometry.

Stephen D. Barnhill, M.D., Chairman and CEO of Health Discovery Corporation, commented, “I am extremely proud of our esteemed scientific team for developing these landmark techniques for analyzing genetic data for more successful biomarker discovery.” Dr. Barnhill continued, “The successful application of these techniques to identify genetic biomarkers for clinically significant prostate cancer and BPH (Benign Prostatic Hypertrophy) demonstrates the power of these newly created biomarker discovery tools.”

A biomarker is a characteristic that is objectively measured and evaluated as an indicator of normal biologic or pathogenic processes or pharmacological responses to a therapeutic intervention. The FDA recently introduced a set of initiatives to accelerate the approvals of diagnostics and new drugs by integrating biomarkers and pharmacogenomic tests into the drug discovery and development steps including clinical trials.

Janet Woodcock, M.D., Acting Deputy Commissioner for Operations, FDA, explained that ’personalized medical treatment’ is now one step closer, further stating, “This new technology will allow medicines to be uniquely crafted to maximize their therapeutic benefits and minimize their potential risks for each patient.”

The FDA’s Press Release stated: “Instead of the standard hit-or-miss approach to treating patients, where it can take multiple attempts to find the right drug and the right dose, doctors will eventually be able to analyze a patient’s genetic profile and prescribe the best available drug therapy and dose from the start. Both the guidance and a new Web page are part of a broad effort underway at FDA to foster pharmacogenomics during drug development.”

“We hope ultimately to bring pharmacogenomics, a way in which to foster the personalizing of medicine, to every healthcare professional’s prescription pad for the benefit of their patients and U.S. consumers,” said Dr. Woodcock.

The FDA Guidance for Industry: Pharmacogenomic Data Submissions released on 3/22/2005 can be read in its entirety at http://www.fda.gov/cber/gdlns/pharmdtasub.pdf

Health Discovery Corporation is a systems biology-oriented biomarker and pathway discovery company, which provides all aspects of First-Phase Biomarker Discovery(SM). The Company was established to provide pharmaceutical and diagnostic companies worldwide with newly discovered biomarkers used to create more accurate diagnostic tests, novel drug targets for more personalized medicines and new methods for detecting patients “at-risk” for toxicity-related events, thereby providing safer medications. Founded in September 2003, the Company is headquartered in Savannah, GA. For more information contact: Stephen D. Barnhill, M.D. of Health Discovery Corporation, 1-800-965-3198 or barnhillmd@sprynet.com.

This news release contains “forward-looking statements” within the meaning of Section 27A of the Securities Acts of 1933 and Section 21E of the Securities Exchange Act of 1934. Although the Company believes that the expectations reflected in such forward-looking statements are reasonable, it can give no assurance that such expectations will prove correct.

Contact Information

Stephen D. Barnhill, M.D.

Media Contact

Health Discovery Corporation

Contact via E-mail